Specialty
A preprint reports valid-and-unique molecular yields and more distinct elite architectures, while a digit-image control favored Soft on distribution matching.
Scientific publication4 min read
A study of 139 Beijing adults found strong internal performance when machine-learning models separated phlegm-dampness and balanced constitutions, but larger validation is still needed.
Frontiers in endocrinology4 min read
A machine-learning model identified concurrent fear of movement in older patients after coronary procedures, with strong results in a time-separated test group but important limits on wider use.
Frontiers in medicine4 min read
A model built from six clinical measures performed better than three comparison methods in an internal test of 518 children with allergic rhinitis. The study found associations involving IgE, Vitamin D, BMI, sleep and screen time, but it did not show that any of these factors causes ADHD or that changing them would alter symptoms.
Frontiers in public health5 min read
In a retrospective study, LightGBM ranked in-hospital mortality risk in a held-out ICU cohort and an external database, but only 30.3% of external high-risk predictions were followed by death.
Frontiers in neurology5 min read
Among 768 young and middle-aged adults receiving maintenance hemodialysis, 40.23% were in paid work at survey time, and a random-forest model performed well in an independent group of 203 patients.
Frontiers in public health4 min read
Researchers compared machine-learning and Cox models for predicting recorded fasting-glucose-defined prediabetes in adults whose baseline glucose was normal. The selected model performed moderately in internal and hospital-based external testing, but the study did not test whether using it improves care.
Frontiers in endocrinology4 min read
Researchers found immune and tissue-related gene signals in separate datasets on disc degeneration and osteoporosis, but say the findings need larger, clinically matched human studies.
Frontiers in immunology5 min read
A theoretical preprint proposes a way to compress weighted graphs and trained neural networks with an explicit error budget, but its demonstration covers only three post-training cases.
Scientific publication4 min read
A constructed example cuts constrained risk in half, but the classical ordering returns when the model class is unrestricted.
Scientific publication5 min read
A new model-auditing method called ICON was designed to show which supplied concepts a deep network relies on, even when those concepts overlap. Tests on synthetic, dermoscopic and neuroimaging models found lower simulation error and clearer signals about image artifacts and demographic correlations.
Scientific publication5 min read
A constrained-reinforcement-learning approach for distilling reasoning into smaller language models recorded the highest reported reasoning success rate across the tested settings, with mixed but often competitive final-answer results.
Scientific publication3 min read
In synthetic AI teams, changing inputs was linked to a sharp rise in feedback, while training on the resulting records was associated with higher success in several benchmark comparisons.
Scientific publication3 min read
ProCTI had the best mean MAE across five time-series datasets under simulated random missingness, while BRITS was best for Weather and Stock in attribute-wise tests.
Scientific publication3 min read
A preprint reports that OPMD outperformed tested distillation baselines on several math and code benchmarks, while its broader reach remains untested.
Scientific publication4 min read
A theoretical preprint examines queue scheduling when service success depends on job context and service cannot be interrupted. It reports near-optimal theoretical guarantees when the horizon is known, but a positive-regret barrier when it is not.
Scientific publication5 min read
A graph-explanation method reported pure edge-level differential privacy for its complete output and retained most of a non-private benchmark ceiling at a privacy budget of 8. The results also point to public graph disclosure and candidate selection as major limits on usefulness.
Scientific publication4 min read
A preprint reports that iSOMA-AR, a version of the iSOMA optimizer that learns a search orientation, beat its baseline on many BBOB conditions, but its gains did not carry over uniformly to CEC or VQE tests.
Scientific publication4 min read
A computational study found robust versions of LassoNet often performed better than mean-squared-error training when responses were contaminated, while clean-data results were mostly similar.
Scientific publication4 min read
A new preprint proposes an embedding method based on Finsler geometry and reports recovery of direction in synthetic manifold and graph experiments.
Scientific publication4 min read
A preprint describes a gradient-based way to filter training units and reports gains in reinforcement learning, math reasoning and preference optimization, alongside higher AIME training costs.
Scientific publication4 min read
The modeling paper says its safeguards depend on declared assumptions, while one end-to-end index walk found that measured penalties exceeded the selected rule's edge.
Scientific publication5 min read
A preprint reports that a two-stage representation-learning method produced the highest reported accuracy on four public multi-view clustering benchmarks, while additional tests examined its handling of shared and view-specific information.
Scientific publication3 min read
Chronos-2 led a two-network test of zero-shot district-heating forecasts, but weather sensitivity, gains from retrained baselines and limited generalization complicated the picture.
Scientific publication3 min read
An arXiv preprint reports lower short- and long-horizon forecast errors for DecoVAE, alongside faster execution and a smaller model on seven time-series benchmarks.
Scientific publication4 min read
A preprint describes a Frame Kernel Method for learning partial differential equations with multiple spatial scales. It reports the lowest error on most tested benchmark problems, while its proposed explanation for unusually fast convergence remains a conjecture.
Scientific publication4 min read
A verifier-based method recorded sizable gains over outcome-level GRPO on ALFWorld and WebShop, while its audits showed that proof-based credit was sometimes unavailable.
Scientific publication4 min read
An arXiv preprint combines a worst-case analysis of softmax approximation rank with a limited learned-head audit, finding a sharp intrinsic geometry law but no added held-out signal from native coordinates.
Scientific publication5 min read
A conceptual note argues that Monte Carlo Tree Search can be understood as every-visit Monte Carlo control when the comparison is limited to trajectory sampling and Monte Carlo action-value updating. The claim clarifies terminology and computational scope, but does not compare performance.
Scientific publication4 min read
A theoretical and synthetic analysis finds that conditional flow matching can replace endpoint likelihood calculations only when specific residual errors cancel. In on-policy training, the shortcut may still improve reward even when its likelihood ratios are far from exact.
Scientific publication5 min read
A preprint introduces egRUE, a method that combines uncertainty scoring with feature-level explanations; its reported gains came from benchmark tests and a small BloodMNIST expert study.
Scientific publication5 min read
Gibbs-family methods led the aggregate scores in Traffic Hourly, Electricity Hourly and Solar Weekly, but classical baselines remained on top in some M4 frequency and disagreement groups.
Scientific publication4 min read
A theoretical and simulation study suggests that private mean estimation can outperform non-private estimation over time when leakage-participation feedback is strong enough.
Scientific publication5 min read
D-TAIA combined parameter-efficient language-model adaptation, domain-aware pre-training and retrieval, then matched or improved on LLM and RNN baselines across four event logs.
Scientific publication5 min read
Spectral and frequency-based features gave the clearest signal for detecting respiratory events in ballistocardiography recordings, with nonlinear classifiers performing strongly when each patient was held out for testing. The results point toward compact systems, but remain limited to one hospital-based sensor setup and cohort.
Scientific publication5 min read
A preprint reports higher average accuracy, lower variability and better average ranks for a residual-guided neural-network procedure tested against RVFL, ELM and BLS baselines on 71 UCI datasets.
Scientific publication4 min read
A computational preprint reports that TransMod had the lowest listed forecasting errors in New York City and Chicago and remained competitive when ride-hailing data were limited.
Scientific publication4 min read
A mathematical preprint reports a proof of Colombo's determinant conjecture for even-dimensional difference-power matrices with pairwise-distinct real nodes. It also gives an exact rank formula and determinant sign rule, while the formal verification described covers the odd-exponent derivation.
Scientific publication5 min read
A computational study reported zero mean final error for Mycelial Search on one benchmark function at two tested dimensions and the lowest reported mean on another at the higher dimension, while other tests showed uneven performance.
Scientific publication4 min read
A preprint describes a mixed-precision approach that assigns bit widths layer by layer using sensitivity estimates and reports quality gains near three-bit compression, while AWQ remains faster in the tested speed comparison.
Scientific publication4 min read